Space-limited U-shape bend is a safety-critical scenario that requires the high maneuverability of vehicles. However, due to the non-holonomic nature of the vehicle, it is difficult to perform flexible U-turns without intricate adjustments, which is detrimental to the efficient execution of tasks. To address these issues, this work incorporates the drifting maneuver of the vehicle and proposes a planning and control framework for time-space efficient passing in constrained U-shape bends. First, a dual-track, 3-Dof vehicle model is developed, incorporating load transfer effects and nonlinear tire forces to enhance trajectory precision. Based on this model, a nonlinear optimization-based planner generates time-optimal, space-efficient, and drift-compatible trajectories while ensuring dynamic feasibility. Finally, a multilayer controller is designed for precise trajectory tracking, integrating a trajectory error feedback compensator, a dynamic state feedforward-feedback regulator, and a model inversion-based actuator controller. Simulation experiments in CarSim validate the proposed framework, demonstrating significant improvements in spatial efficiency and completion time. The results highlight its effectiveness in enhancing autonomous vehicle maneuverability for high-performance applications in constrained environments.

Abstract The safe operation of gas pipelines is crucial for the safety of residents’ lives and property. However, accurately detecting defects within these gas pipelines is a challenging task. To improve the accuracy of defect detection in pipeline DR images with small sample sizes, we propose an enhanced Faster RCNN model based on a Smooth Variational Autoencoder and Enhanced Detection Head (S-EDH-Faster RCNN). This model leverages a smooth variational autoencoder to reconstruct features and enhances classification scores through an improved detection head, thereby boosting overall detection accuracy. In detail, to address the issue of scarce training samples for new categories, we design a smooth variational autoencoder to reconstruct features that better fit the distribution of training data. Furthermore, to refine classification precision, we present an enhanced detection head that incorporates a convolutional block attention-based center point classification calibration module, which strengthens classification-related portions of the RoI features and adjusts classification scores accordingly. Finally, to effectively learn characteristics of novel class samples, we introduce an adaptive fine-tuning method that adaptively updates key convolutional kernels during the fine-tuning stage, enabling the model to generalize better to novel classes. Experimental results demonstrate that our approach achieves superior detection performance over state-of-the-art models on both the home-made PIP-DET dataset and the publicly available NEU-DET dataset, demonstrating its effectiveness.

The working conditions of gas pipelines directly impact urban populations and factory operations. However, accurate and rapid detection of gas pipeline defects is challenging. To improve the accuracy of gas pipeline defect detection , we propose an improved RefineDet (Im-RefineDet) for gas pipeline defect detection, in which the improvement is carried out from the backbone network and the detection head. Specifically, to extract richer features, we design an improved CrossFormer as the backbone network. It first adopts a small convolutional cross-scale embedding layer to perform convolution, and then uses stripe window self-attention in vertical and horizontal directions in sequence to extract different features. In the detection head, we present a Double Attention Decouple Head (DADH) for classification and localization, enabling the model to perform independent optimization of the two branches. DADH employs spatial-aware and scale-aware attention to acquire multi-scale features, subsequently conducting classification and localization separately to derive final detection outcomes. Additionally, we apply channel pruning to the model to achieve a lightweight design, improving computational efficiency without significantly compromising detection performance. Experimental results, derived from an in-house developed gas pipeline defect image dataset, as well as two publicly available datasets — the NEU-DET dataset and the PCB dataset — demonstrate the effectiveness of the proposed Im-RefineDet. These results highlight its superior performance compared to state-of-the-art methods, further validating its robustness and adaptability across diverse scenarios. Specifically, the model achieves the mean Average Precision (mAP) of 92.6% on the gas pipeline defect image dataset, 77.8% on the NEU-DET dataset, and 99.2% on the PCB defect detection dataset.

Prediction is a vital component of motion planning for autonomous vehicles (AVs). By reasoning about the possible behavior of other target agents, the ego vehicle (EV) can navigate safely, efficiently, and politely. However, most of the existing work overlooks the interdependencies of the prediction and planning module, only connecting them in a sequential pipeline or underexploring the prediction results in the planning module. In this work, we propose a framework that integrates the prediction and planning module with three highlights. First, we propose an ego-conditioned model for causal prediction, with the introduced edge-featured graph transformer model, the impact the ego future maneuver poses to the target vehicles is demonstrated. Second, we develop a motion planner based on ‘dynamic voxels’ in the spatio-temporal domain, enabling the time-to-collision criterion evaluation and the optimal trajectory generation in continuous space. Third, the prediction and planning modules are coupled in a closed-loop and efficient form. Specifically, taking each maneuver as a cluster, representative trajectory primitives are generated for conditional prediction, and conversely, prediction results are used to score the primitives as guidance, which alleviates the duplicated callback of the prediction module. The simulations are conducted in overtaking, merging, unprotected left turns, and also scenarios with imperfect social behaviors. The comparison studies demonstrate the better safety assurance and efficiency of the proposed model, and the ablation experiments further reveal the effectiveness of the new ideas.

Uncontrolled intersections with interaction and uncertainties are challenging for autonomous vehicles (AV) to manage. In this work, we propose a decision-making model specific to intersections with emphasis on three aspects. First, behavior estimation of the social vehicles’ (SVs) is essential for risk avoidance. We try to improve prediction accuracy by predicting the intentions and driving styles of SVs in advance and doing adaptive goal sampling. Second, the uncertainty from the prediction results should be considered in the decision-making process. For this, a risk-aware framework is developed, composed of a Subordinate Driver (SD) and a Primary Driver (PD) for decision-making and planning. Particularly, in SD, the prediction-guided strategy tree is built to search for an optimal strategy with observation and action branch trimming, which employs the prediction results for risk assessment. In PD, to mimic the both-way negotiation among vehicles, the level-k game model is deployed to determine the action in the players’ best interest and update the estimation of driving styles. Third, the generated maneuver is required to be evaluated in a closed-loop simulation. A ‘semi-autonomous’ control model is designed, which is a combination of the dataset and the stochastic sampling model. The results of ablation experiments verify the function of each module. The case studies and comparison experiments demonstrate the effectiveness of the framework in highly interactive intersections.

Autonomous driving, including intelligent decision-making and path planning, in dynamic environments (like highway) is significantly more difficult than the navigation in static scenarios because of the additional time dimension. Therefore, correlating the time dimension and the space dimension through prediction to create a spatio-temporal navigation map can make decision-making and path planning in such kinds of environment much easier. In this article, NGSIM data is analysed and processed from the perspective of the ego-vehicle (using the data as an ego-vehicle’s perception results). Based on the data, we develop an LSTM (Long-Short Term Memory)-based framework to predict possible trajectories of multiple surrounding vehicles within a certain range of the ego-vehicle. Then, the multiple predicted trajectories in a series of continuous dynamic highway scenes are projected into a spatio-temporal domain to create an octree map. Thus, dynamic targets and static obstacles can be unified into the same domain or map so that the dynamic disturbance problem for autonomous driving in highway environments can be resolved. Experimental results show that the proposed model is capable of predicting all the future trajectories around the ego-vehicle efficiently and the corresponding spatio-temporal map can be generated accurately in different dynamic scenarios.

As the vital factor of vehicle behavior understanding and prediction, vehicle taillight recognition is an important technology for autonomous driving, especially in diverse actual traffic scenes full of dynamic interactive traffic participants. However, in practical application, it always faces many challenges, such as ‘variable lighting conditions’, ‘non-uniform taillight standards’ and ‘random relative observation pose’, which lead to few mature solutions in current common autopilot systems. This work proposes an action-state joint learning-based vehicle taillight recognition method on the basis of vehicles detection and tracking, which takes both taillight state features and time series features into account, consequently getting practicable results even in complex actual scenes. In detail, vehicle tracking sequence is used as input and split into pieces through a sliding window. Then, a CNN-LSTM model is applied to simultaneously identify the action features of brake lights and turn signals, dividing taillight actions into five categories: None, Brake_on, Brake_off, Left_turn, Right_turn. Next, the brightness of high-position brake light is extracted through semantic segmentation and combined with taillight actions to form higher-level features for taillight state sequence analysis. Finally, an undirected graph model is used to establish the long-term dependence between successive pieces by analysing the higher-level features, thus inferring the continuous taillight state into:$off$,$brake$,$left$,$right$. Datasets including daytime, nighttime, congested road, highway, etc. were collected, tested and published in our work to demonstrate its effectiveness and practicability.

Trajectory planning for the unmanned vehicle in the complex environment has always been a challenging task. Planned trajectory with the corresponding target velocity or acceleration sequence must be collision-free guaranteed and as comfortable as possible on the premise of obeying the traffic rules and interaction with other dynamic social vehicles. To meet this requirement, this paper proposes a framework for trajectory planning based on spatio-temporal map. Due to the time layer architecture in the map, the trajectory can be generated with velocity and acceleration simultaneously, and the whole trajectory is constrained within a ‘safety strip’, resulting in an efficient and safety guaranteed trajectory. The framework is composed of three sections: rough search, fine optimization and safety strip-based collision avoidance. For rough search, we propose an improved A* algorithm implemented in the discrete time layer to find out the suboptimal states efficiently. In fine optimization, the B-spline curve is exploited to connect the searched states into a continuous trajectory. And the optimal control points of B-spline are further grouped into several segments, forming the safety strip which is actually the distribution space of the planned trajectory. If necessary, an adjustment will be applied to keep the strip away from the collision zone, making the entire trajectory completely collision-free. Experiments on both public dataset and self-driving simulator show that the proposed framework can adapt to different kinds of complex traffic scenes well.

Intelligent decision making and efficient trajectory planning are closely related in autonomous driving technology, especially in highway environment full of dynamic interactive traffic participants. This work integrates them into a unified hierarchical framework with long-term behavior planning (LTBP) and short-term dynamic planning (STDP) running in two parallel threads with different horizon, consequently forming a closed-loop maneuver and trajectory planning system that can react to the dynamic environment effectively and efficiently. In LTBP, a novel voxel structure and the ‘voxel expansion’ algorithm are proposed for the generation of driving corridors in 3D configuration, which involves the prediction states of surrounding vehicles. By using Dijkstra search, the maneuver with minimal cost is determined in form of voxel sequences, then a quadratic programming (QP) problem is constructed for solving the optimal trajectory. And in STDP, another small-scaled QP problem is performed to track or adjust the reference trajectory from LTBP in response to the dynamic obstacles. Meanwhile, a Responsibility-Sensitive Safety (RSS) Checker keeps running at high frequency for real-time feedback to ensure security. Experiments on real data collected in different highway scenarios demonstrate the effectiveness and efficiency of our work.

Trajectory prediction for vehicles is a popular subject since it is beneficial for efficient and secure trajectory planning. In structured traffic scenarios, the behaviour and motion of vehicles are heavily dependent on the social interaction constraints, such as road geometry and surrounding vehicles, and the kinematics model constraints, such as continuous heading and maximum acceleration. To take these factors into account, we analyse the particular characteristics of driving vehicles and propose a model that predicts the possible and feasible trajectory for host vehicle in 3 seconds. In this model, the trajectory of host vehicle takes the center-line as reference, imitates the leader vehicle and focuses on the social vehicles through attention concentration mechanism (ACM) with spatial and temporal information encoded in a fusion hidden state. Furthermore, in order to make the trajectory feasible for vehicle dynamics and kinematics, we introduce a prediction diagnosis method to check the continuous heading and maximum acceleration condition, pruning and adjusting the prediction candidates. Experiments on released public datasets show that this framework can well evaluate the traffic interactions and forecast the trajectory more accurately than common networks.